© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6048
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to molecular biology and genetic analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    });*/
    -0.61
    Portale
    -0.60
    }');
    -0.59
     />';
    -0.58
    MigrationBuilder
    -0.57
    VolleyError
    -0.57
     \%)$
    -0.57
    KURZBESCHREIBUNG
    -0.55
    })));
    -0.55
    :])
    -0.54
    POSITIVE LOGITS
     Miracle
    0.54
     שוליים
    0.50
    permitAll
    0.48
    otechnology
    0.48
     وصلة
    0.48
    קישורים
    0.48
    conver
    0.47
    EndTag
    0.46
    FieldBuilder
    0.45
    DockStyle
    0.45
    Activations Density 3.213%

    No Known Activations